使用 css 选择器 excel vba 从网站抓取数据

Question

我正在尝试使用 CSS 选择器从网站上抓取特定数据。我在 QHar 的帮助下取得了成功，但现在的要求已经改变。这是我下面的代码：

代码

Public Sub CompanyData2()

Dim html As HTMLDocument, ws As Worksheet, re As Object

Set re = CreateObject("VBScript.RegExp")
re.Pattern = "\s{2,}"
Set ws = ThisWorkbook.Worksheets("Sheet1")
Set html = New HTMLDocument

With CreateObject("MSXML2.XMLHTTP")
    .Open "GET", "https://www.bizi.si/iskanje?q=", False
    .send
    html.body.innerHTML = .responseText
End With

ws.Range("A4").Value = re.Replace(Join$(Array(html.querySelector("td.item a").innerText), ", "), Chr$(32))
ws.Range("A5").Value = re.Replace(Join$(Array(html.querySelector("td.item + td.item").innerText), ", "), Chr$(32))
ws.Range("B6").Value = re.Replace(Join$(Array(html.querySelector("td.item + td.item + td.item + td.item").innerText), ", "), Chr$(32))

End Sub

结果如下：

网站

我想像这样在表格 1 A3 上提取公司名称：

谢谢。

Answer 1

您需要在 A1 中使用REPROMAT，然后在发出初始查询后，您必须访问实际的公司页面以获取显示的公司名称。如果您直接使用公司网址，那么您可以跳过第一个请求并从第二个请求开始使用代码。

Public Sub CompanyData()
    Dim html As HTMLDocument, ws As Worksheet, nodes As Object

    Set ws = ThisWorkbook.Worksheets("Sheet1")
    Set html = New HTMLDocument

    With CreateObject("MSXML2.XMLHTTP")
        .Open "GET", "https://www.bizi.si/iskanje?q=" & Application.EncodeURL(ws.Range("A1").Value), False
        .send
        html.body.innerHTML = .responseText

        Set nodes = html.querySelectorAll("td.item")

        With ws
            .Range("A4").Value = nodes.Item(0).FirstChild.innerText
            .Range("A5").Value = nodes.Item(1).innerText
            .Range("A6").Value = "DŠ: " & nodes.Item(3).innerText
        End With

        .Open "GET", html.querySelector("[id$=linkCompany]").href, False
        .send
        html.body.innerHTML = .responseText
        ws.Range("A3") = html.querySelector("#ctl00_ctl00_cphMain_cphMainCol_CompanySPLPreview1_labTitlePRS").innerText
    End With
End Sub